QW

Qwen2 0.5B NuminaMath TIR v1

QwenGGUF by mradermacherUpdated 2024-08-20
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.3 GB
Quick answer

Qwen2 0.5B NuminaMath TIR v1 needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.3 GB (Q3_K_S) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Qwen2 0.5B NuminaMath TIR v1 – a compact math‑focused model

Qwen2 0.5B NuminaMath TIR v1 is a 0.494 billion‑parameter model trained on 32768 context tokens. It is released under the apache‑2.0 license and is available in multiple GGUF quantizations. The model is tailored for mathematical reasoning tasks.

Good at

  • Mathematical reasoning
  • Short‑form text generation
  • Low‑resource inference

Limits

  • No vision support
  • Limited context to 32768 tokens
  • Requires 8 k context for memory estimates

Best for

  • Math tutoring
  • Code documentation snippets
  • Quick math queries

Who it’s for. Developers and researchers needing a lightweight math model for local inference. It is suitable for environments with limited GPU memory and for use with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
IQ3_S0.3 GB 0.9 GB
Fits Get file →
IQ3_XS0.3 GB 0.9 GB
Fits Get file →
Q2_K0.3 GB 0.9 GB
Fits Get file →
IQ3_M0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.39 GB) or Q4_K_M (0.40 GB) – memory usage is about 1 GB at 8 k context. For 4 GB VRAM, choose Q3_K_S (0.34 GB) or IQ3_S (0.34 GB). Larger models like F16 (0.99 GB) need 1.6 GB memory at 8 k context.

What GPU do you need for Qwen2 0.5B NuminaMath TIR v1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (1.0 GB file, about 1.6 GB in use).

Which Qwen2 0.5B NuminaMath TIR v1 quant should you choose?

Q4_K_M is the usual starting point for Qwen2 0.5B NuminaMath TIR v1: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.5 GB, about 1.3 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 0.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,628
Last updated2024-08-20

Frequently asked questions about Qwen2 0.5B NuminaMath TIR v1

How much VRAM does Qwen2 0.5B NuminaMath TIR v1 need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen2 0.5B NuminaMath TIR v1 on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2 0.5B NuminaMath TIR v1 GGUF?

It depends on the quant: Q3_K_S is 0.3 GB, IQ3_S is 0.3 GB, IQ3_XS is 0.3 GB, Q2_K is 0.3 GB, IQ3_M is 0.3 GB, IQ4_XS is 0.4 GB and 9 more.

What context length does Qwen2 0.5B NuminaMath TIR v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download Qwen2 0.5B NuminaMath TIR v1 GGUF?

The files are on Hugging Face in the mradermacher/Qwen2-0.5B-NuminaMath-TIR-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen2 0.5B NuminaMath TIR v1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen2 0.5B NuminaMath TIR v1 on 8 GB VRAM?

Yes, use a quant like Q4_K_S or Q4_K_M; memory usage is roughly 1 GB at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →